code-review

Review code diffs for correctness, security, style, tests, and performance.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/SalesTeamToolbox/frood --skill code-review-salesteamtoolbox
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/SalesTeamToolbox/frood/tree/main/skills/builtins/code-review
Command: npx skills add https://github.com/SalesTeamToolbox/frood --skill code-review-salesteamtoolbox

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Code review reduces the risk of shipping incorrect, insecure, or poorly tested changes by turning a pull request into structured, actionable feedback.

Core Features & Use Cases

  • Correctness review: checks whether changes match the stated intent, cover edge cases, and use correct return types and error handling.
  • Security review: flags common vulnerabilities such as injection issues, unsafe input handling, missing auth checks, and SSRF-prone URL handling.
  • Quality validation: evaluates test coverage (including error paths and edge cases), style consistency, and performance concerns like unnecessary loops or N+1 patterns.
  • Use case: Review a PR that modifies request validation and data access to ensure it handles null inputs safely, adds deterministic tests for failure modes, and maintains consistent formatting with the existing codebase.

Quick Start

Ask the AI to review the following pull request diff for correctness, security, tests, style, and performance, and to respond using the required summary and severity-tagged findings format.

Frequently Asked Questions about code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review a pull request for security flaws and test gaps?

A pull request review checks correctness, security, test coverage, style, and performance by analyzing the diff to identify issues like unsafe input handling, missing auth checks, and N+1 query patterns. It produces structured findings with severity levels and actionable suggestions.

How do I check code correctness when refactoring existing logic?

To check code correctness when refactoring, you analyze the modified logic to ensure it matches the stated intent, covers edge cases, uses correct return types, and handles errors properly. This validation confirms the refactoring does not break existing behavior.

What is the best way to find performance issues like N+1 queries in a diff?

The best way to find performance issues like N+1 queries in a diff is to evaluate the proposed changes for unnecessary loops and inefficient data access patterns. This process flags performance concerns during the review before the code is merged.

Can I use automated code review for debugging-driven analysis?

Yes, you can use automated code review for debugging-driven analysis. It applies systematic validation to proposed changes, identifying correctness issues and edge cases while providing concrete file and line references to help locate bugs.

Does code review work without configuring external dependencies or components?

Yes, code review works without configuring external dependencies or components. You can directly provide a pull request diff and request a structured analysis of correctness, security, tests, style, and performance without any environment setup.